Study finds articulation gaps in every field: shared preferences that can't be put into words
sanmikoyejo · x · 2026-10-29
The core finding of the thread: articulation gaps exist in every field studied — components of shared preference that cannot be verified or put into words, as far as measurement allows.
Yet humans still agree on what they mean. The author flags implications for AI slop, safety, discovery, and anything else relying on such tacit knowledge.
More from Research
- AI Now Discovers Faster Than Institutions Can Verify: The 200M-Protein Integrity Paradox — mikeflache · 2026-10-29
- FrontierCS 2 reshuffles rankings: Claude Opus 5.5 tops FCI as DeepSeek 1017 degrades — teortaxesTex · 2026-10-29
- Constitutional grafting: character training for open models under $500, skipping $440k of compute — voooooogel · 2026-10-29
- Transformer layers turned into a full-fledged symbolic CPU — yshan2u · 2026-10-29
- NanoDreamer: A 750K-parameter world-model agent trained on a MacBook M5 Pro plays 5 MinAtar games — CatAstro_Piyush · 2026-10-29
- Why You Can't Just Remove Positional Embeddings: Self-Attention Is Permutation Equivariant — cneuralnetwork · 2026-10-29